Re: Asymmetric multiprocessing?

Rogier Wolff (R.E.Wolff@BitWizard.nl)
Sun, 3 May 1998 09:09:51 +0200 (MET DST)


Alan Cox wrote:
>
> > systems like Amiga/68k + Linux/PPC. Memory bus congestion is probably
> > going to be a serious problems since those card have not been designed with
> > the memory bandwith to supply both cpus.
> >
> > For above configuration I'd say ignore the '020. It just produces very
> > serious congestion of the memory bus on the motherboard.
>
> Or use it as a glorified DMA controller/IRQ buffer

This popped up yesterday: if you want to build a large cluster of
machines with humungous amounts of processing power (beowulf), would you
put one or two processors in each node?

My suggestion was to use two. However someone remarked that you'd
congest the memory bus. In short, it depends on the application.

Now as an alternative I suggested putting one REAL processor on each
node (P-II/400) and one that does all the nasty side-tasks (say a
P-II/200)

That should allow the compute-intensive task to run at 100% CPU (not
just 98%) leaving all the interrupts and other stuff to the other
processor.

My guess is that this will hapen in 50% of the cases, and in the other
50% of the cases, the CPU-intensive task will end up on the P-II/200
and the 400MHz beast will be idle except for servicing interrupts....

Roger.

-- 
If it's there and you can see it, it's REAL      |___R.E.Wolff@BitWizard.nl  |
If it's there and you can't see it, it's TRANSPARENT |  Tel: +31-15-2137555  |
If it's not there and you can see it, it's VIRTUAL   |__FAX:_+31-15-2138217  |
If it's not there and you can't see it, it's GONE! -- Roy Wilks, 1983  |_____|

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu